{
  "schemaVersion": "1.0",
  "item": {
    "slug": "cli-worker",
    "name": "CLI Worker Skill (Kimi CLI)",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/quratus/cli-worker",
    "canonicalUrl": "https://clawhub.ai/quratus/cli-worker",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/cli-worker",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cli-worker",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "AGENTS.md",
      "CHANGELOG.md",
      "README.md",
      "SECURITY.md",
      "SKILL.md",
      "bin/auth/verify.js"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/cli-worker"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/cli-worker",
    "agentPageUrl": "https://openagent3.xyz/skills/cli-worker/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cli-worker/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cli-worker/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "When to use",
        "body": "User asks to delegate a coding task to Kimi or a CLI worker\nIsolated coding task that should run in its own worktree (no git conflicts)\nParallel work: run multiple tasks without blocking the main agent\nHeadless task: run Kimi CLI non-interactively from OpenClaw"
      },
      {
        "title": "Delegation: prefer CLI over sessions_spawn",
        "body": "For a single coding task, use the CLI so the task actually runs:\n\nDo: cli-worker execute \"Your task prompt\" (and optionally --constraint / --success). This runs Kimi CLI in a worktree and returns output.\nAvoid: Using sessions_spawn to delegate to a \"sub-agent\" for the same kind of task. Spawn is known to sometimes create a session that never processes (0 messages). Use sessions_spawn only when you need an ongoing sub-agent conversation with multiple back-and-forth or sessions_send.\n\nAfter any spawn, verify within ~30s: sessions_list with kinds: [\"subagent\"] and/or sessions_history on the child session; if messages stay 0, treat as failed and retry with cli-worker execute instead."
      },
      {
        "title": "Prerequisites",
        "body": "You must install and authenticate the CLI yourself before using this skill. This skill does not store or use any credentials.\n\nKimi CLI installed (uv tool install kimi-cli or install script from code.kimi.com)\nAuthenticated: run kimi then /login in the REPL (user must complete OAuth; cannot be automated)\n\nVerify with: cli-worker verify"
      },
      {
        "title": "How to invoke",
        "body": "# Run a single task (creates worktree if in a git repo)\ncli-worker execute \"Your task prompt\"\n\n# With context\ncli-worker execute \"Create hello.py\" --constraint \"Python 3.11\" --success \"Tests pass\"\n\n# To get full plain-text output for the agent (not only the final answer)\ncli-worker execute \"Your task\" --output-format text\n\n# Check task status (after Kimi writes report)\ncli-worker status <taskId>\n\n# List / remove worktrees\ncli-worker worktree list\ncli-worker worktree remove <taskId>\n\n# Cleanup old worktrees\ncli-worker cleanup --older-than 24"
      },
      {
        "title": "Merge and cleanup",
        "body": "After a task completes, decide whether to keep or discard the work:\n\nTo keep the work: From the main repo (e.g., on main), run:\ngit merge openclaw/<taskId>\ncli-worker worktree remove <taskId>\n\n\nTo discard: Run cli-worker worktree remove <taskId> directly, or rely on cli-worker cleanup --older-than N."
      },
      {
        "title": "Install",
        "body": "CLI (required for execute/verify): Must be on PATH where the agent runs. From the repo: npm install && npm run build && npm link. (From npm: npm install -g @sqncr/openclaw-cli-agent-skill.) If the agent gets \"command not found\", run npm link from the repo and restart the gateway.\nSkill discovery: From the repo run npm run install-skill to symlink into ~/.openclaw/skills/cli-worker. Restart gateway or new session after that."
      },
      {
        "title": "OpenClaw integration",
        "body": "Symlink or copy skills/cli-worker/ to ~/.openclaw/skills/cli-worker/ so agents can discover it\nOptional config: ~/.openclaw/openclaw.json with worktree.basePath for worktree location"
      }
    ],
    "body": "CLI Worker Skill (Kimi CLI)\nWhen to use\nUser asks to delegate a coding task to Kimi or a CLI worker\nIsolated coding task that should run in its own worktree (no git conflicts)\nParallel work: run multiple tasks without blocking the main agent\nHeadless task: run Kimi CLI non-interactively from OpenClaw\nDelegation: prefer CLI over sessions_spawn\n\nFor a single coding task, use the CLI so the task actually runs:\n\nDo: cli-worker execute \"Your task prompt\" (and optionally --constraint / --success). This runs Kimi CLI in a worktree and returns output.\nAvoid: Using sessions_spawn to delegate to a \"sub-agent\" for the same kind of task. Spawn is known to sometimes create a session that never processes (0 messages). Use sessions_spawn only when you need an ongoing sub-agent conversation with multiple back-and-forth or sessions_send.\n\nAfter any spawn, verify within ~30s: sessions_list with kinds: [\"subagent\"] and/or sessions_history on the child session; if messages stay 0, treat as failed and retry with cli-worker execute instead.\n\nPrerequisites\n\nYou must install and authenticate the CLI yourself before using this skill. This skill does not store or use any credentials.\n\nKimi CLI installed (uv tool install kimi-cli or install script from code.kimi.com)\nAuthenticated: run kimi then /login in the REPL (user must complete OAuth; cannot be automated)\n\nVerify with: cli-worker verify\n\nHow to invoke\n# Run a single task (creates worktree if in a git repo)\ncli-worker execute \"Your task prompt\"\n\n# With context\ncli-worker execute \"Create hello.py\" --constraint \"Python 3.11\" --success \"Tests pass\"\n\n# To get full plain-text output for the agent (not only the final answer)\ncli-worker execute \"Your task\" --output-format text\n\n# Check task status (after Kimi writes report)\ncli-worker status <taskId>\n\n# List / remove worktrees\ncli-worker worktree list\ncli-worker worktree remove <taskId>\n\n# Cleanup old worktrees\ncli-worker cleanup --older-than 24\n\nMerge and cleanup\n\nAfter a task completes, decide whether to keep or discard the work:\n\nTo keep the work: From the main repo (e.g., on main), run:\ngit merge openclaw/<taskId>\ncli-worker worktree remove <taskId>\n\nTo discard: Run cli-worker worktree remove <taskId> directly, or rely on cli-worker cleanup --older-than N.\nInstall\nCLI (required for execute/verify): Must be on PATH where the agent runs. From the repo: npm install && npm run build && npm link. (From npm: npm install -g @sqncr/openclaw-cli-agent-skill.) If the agent gets \"command not found\", run npm link from the repo and restart the gateway.\nSkill discovery: From the repo run npm run install-skill to symlink into ~/.openclaw/skills/cli-worker. Restart gateway or new session after that.\nOpenClaw integration\nSymlink or copy skills/cli-worker/ to ~/.openclaw/skills/cli-worker/ so agents can discover it\nOptional config: ~/.openclaw/openclaw.json with worktree.basePath for worktree location"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/quratus/cli-worker",
    "publisherUrl": "https://clawhub.ai/quratus/cli-worker",
    "owner": "quratus",
    "version": "0.3.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/cli-worker",
    "downloadUrl": "https://openagent3.xyz/downloads/cli-worker",
    "agentUrl": "https://openagent3.xyz/skills/cli-worker/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cli-worker/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cli-worker/agent.md"
  }
}